Artificial intelligence on COVID-19 pneumonia detection using chest xray images.

Recent studies show the potential of artificial intelligence (AI) as a screening tool to detect COVID-19 pneumonia based on chest x-ray (CXR) images. However, issues on the datasets and study designs from medical and technical perspectives, as well as questions on the vulnerability and robustness of AI algorithms have emerged. In this study, we address these issues with a more realistic development of AI-driven COVID-19 pneumonia detection models by generating our own data through a retrospective clinical study to augment the dataset aggregated from external sources. We optimized five deep learning architectures, implemented development strategies by manipulating data distribution to quantitatively compare study designs, and introduced several detection scenarios to evaluate the robustness and diagnostic performance of the models. At the current level of data availability, the performance of the detection model depends on the hyperparameter tuning and has less dependency on the quantity of data. InceptionV3 attained the highest performance in distinguishing pneumonia from normal CXR in two-class detection scenario with sensitivity (Sn), specificity (Sp), and positive predictive value (PPV) of 96%. The models attained higher general performance of 91-96% Sn, 94-98% Sp, and 90-96% PPV in three-class compared to four-class detection scenario. InceptionV3 has the highest general performance with accuracy, F1-score, and g-mean of 96% in the three-class detection scenario. For COVID-19 pneumonia detection, InceptionV3 attained the highest performance with 86% Sn, 99% Sp, and 91% PPV with an AUC of 0.99 in distinguishing pneumonia from normal CXR. Its capability of differentiating COVID-19 pneumonia from normal and non-COVID-19 pneumonia attained 0.98 AUC and a micro-average of 0.99 for other classes.

Early experience with COVID-19 patients in a private tertiary hospital in the Philippines: Implications on surge capacity, healthcare systems response, and clinical care.

BACKGROUND: Our healthcare institution was one of the first to see SARS CoV-2 cases in the country. We describe the early COVID-19 experience of a private hospital in the Philippines and discuss the healthcare system response in the setting of surge capacity. METHODS: We reviewed the medical records of adult COVID-19 hospitalized patients admitted in March 2020. We reported their demographic and clinical characteristics using descriptive statistics. RESULTS: Of 40 patients admitted, 23 (57.5%) were male and 19 (47.5%) were aged <60 years. Most (n = 27, 67.5%) had moderate-risk, 9 (22.5%) had high-risk, and 4 (10%) had low-risk COVID-19. SARS-CoV-2 testing took 5.5 (range 1-10) days. Overall mortality rate was 6/40 (15.0%). Clinical cure was documented in all low-risk patients, 25 (92.6%) moderate-risk patients, and only 1 (11.1%) high-risk patient. In response to the surge, the hospital rapidly introduced one-way traffic systems, dedicated screening, triage and Emergency Department areas for COVID-19, a clinical pathway, engineering controls, patient cohorting, and strict infection prevention and control measures. CONCLUSION: Majority of patients recovered from COVID-19. Older age and high-risk pneumonia were associated with poor outcomes. Adaptations to hospital structure and staff were quickly made in response to surge capacity, although our response was hampered by prolonged time to COVID-19 confirmation. Our study underscores the urgent need for rapid adaptive response by the healthcare system to address the surge of cases.